AI agents use mail_create_message to create or update resources in Mcp Mac — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Mac environment.
This tool creates (but does not send) email messages, making it a Write operation that reversibly modifies data. Severity is medium because an AI agent misuse could spam contacts, send phishing emails, or impersonate the user, causing reputational or security harm, but the message must still be sent separately (tool only creates, doesn't auto-send).
From the tool's definition Tool creates new email messages with recipients, subject, and body. Description explicitly states 'Create new email message' which is a write operation that modifies the mail system by adding a new message.
Attacks that exploit this kind of access
Create new email message with recipients, subject, and body. It is categorised as a Write tool in the Mcp Mac MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Mac MCP server in PolicyLayer and add a rule for mail_create_message: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Mac. Nothing to install.
mail_create_message is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the mail_create_message rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for mail_create_message. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
mail_create_message is provided by the Mcp Mac MCP server (samicokar/mcp-mac). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →